Loading [a11y]/accessibility-menu.js
UniParser: Multi-Human Parsing With Unified Correlation Representation Learning | IEEE Journals & Magazine | IEEE Xplore

UniParser: Multi-Human Parsing With Unified Correlation Representation Learning


Abstract:

Multi-human parsing is an image segmentation task necessitating both instance-level and fine-grained category-level information. However, prior research has typically pro...Show More

Abstract:

Multi-human parsing is an image segmentation task necessitating both instance-level and fine-grained category-level information. However, prior research has typically processed these two types of information through distinct branch types and output formats, leading to inefficient and redundant frameworks. This paper introduces UniParser, which integrates instance-level and category-level representations in three key aspects: 1) we propose a unified correlation representation learning approach, allowing our network to learn instance and category features within the cosine space; 2) we unify the form of outputs of each modules as pixel-level results while supervising instance and category features using a homogeneous label accompanied by an auxiliary loss; and 3) we design a joint optimization procedure to fuse instance and category representations. By unifying instance-level and category-level output, UniParser circumvents manually designed post-processing techniques and surpasses state-of-the-art methods, achieving 49.3% AP on MHPv2.0 and 60.4% AP on CIHP. We have released our source code, pretrained models, and demos to facilitate future studies on https://github.com/cjm-sfw/Uniparser.
Published in: IEEE Transactions on Image Processing ( Volume: 33)
Page(s): 5159 - 5171
Date of Publication: 12 September 2024

ISSN Information:

PubMed ID: 39264771

Funding Agency:


References

References is not available for this document.